Title

Characterization of a Class of Sigmoid Functions with Applications to Neural Networks

Author(s)/Creator(s)

Anil Ravindran Menon, Syracuse University
Kishan Mehrotra, Syracuse UniversityFollow
Chilukuri K. Mohan, Syracuse UniversityFollow
Sanjay Ranka, Syracuse University

Document Type

Report

Date

11-1994

Keywords

Sigmoid functions, Hypergeometric series, Legendre equation, Fourier transform

Language

English

Disciplines

Computer Sciences

Description/Abstract

Sigmoid functions, whose graphs are "S-shaped" curves, appear in a great variety of contexts, such as the transfer functions in many neural networks. Their ubiquity is no accident; these curves are the among the simplest non-linear curves, striking a graceful balance between linear and non-linear behavior.

Additional Information

School of Computer and Information Science, Syracuse University, SU-CIS-94-7

Authors later published: Anil Menon, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka, Characterization of a Class of Sigmoid Functions with Applications to Neural Networks, Neural Networks, Volume 9, Issue 5, July 1996, Pages 819-835, ISSN 0893-6080, http://dx.doi.org/10.1016/0893-6080(95)00107-7.

Recommended Citation

Menon, Anil Ravindran; Mehrotra, Kishan; Mohan, Chilukuri K.; and Ranka, Sanjay, "Characterization of a Class of Sigmoid Functions with Applications to Neural Networks" (1994). Electrical Engineering and Computer Science - Technical Reports. 152.
https://surface.syr.edu/eecs_techreports/152

Source

local